Attacks against machine learning — an overview
This blog post surveys the attacks techniques that target AI (Artificial Intelligence) systems and how to protect against them.
machine-learning  cybersecurity 
yesterday
[1806.07060] A model-driven approach for a new generation of adaptive libraries
Efficient high-performance libraries often expose multiple tunable parameters to provide highly optimized routines. These can range from simple loop unroll factors or vector sizes all the way to algorithmic changes, given that some implementations can be more suitable for certain devices by exploiting hardware characteristics such as local memories and vector units. Traditionally, such parameters and algorithmic choices are tuned and then hard-coded for a specific architecture and fo...
machine-learning  gpu  libraries 
2 days ago
Machine Learning Kaggle Competition Part Two: Improving
I recommend against the “lone genius” path, not only because it’s exceedingly lonely, but also because you will miss out on the most important part of a Kaggle competition: learning from other data…
feature-learning 
2 days ago
Formal Methods in Practice – eSpark Engineering Blog – Medium
How do we harden a system against race conditions? When it uses a complex cache? When it requires a global state? We could blanket our system in tests, hope we’ve covered every possible edge case…
formal-methods 
2 days ago
Robot antenna - Introduction | Raspberry Pi Projects
In this resource you will build a cardboard robot with a real flashing LED antenna, and use Scratch to create a robot twin that beeps.

education-activity 
5 days ago
New insights on the practices of documentation of open-source software | Berkeley Institute for Data Science
The Berkeley Institute for Data Science (BIDS) hosts research, events, and tool development focused on facilitating data-intensive research. Today, computational research and data analytics relies on complex ecosystems of open source software (OSS) tools and libraries. Software documentation is crucial to help researchers discover and use these tools, to help build a community ecosystem of data science packages, and to define best practices in the field. However, software documentati...
documentation  open-source 
8 days ago
GitHub - DataSquad/Awesome_DataScienceTraining: An Awesome list of machine-learning, data science, data visualization training, and related programing training resources
Awesome_DataScienceTraining - An Awesome list of machine-learning, data science, data visualization training, and related programing training resources
machine-learning  learning  tutorials  resources 
9 days ago
Large Graph Visualization | NASA Data Analytics Team
Wikipedia Map is a tool for visualizing topics by exploring the connections between Wikipedia pages.
graph-database  visualization  networks 
10 days ago
GitHub - trallard/ReproduciblePython: Workshop materials for PyCon 2018 workshop on reproducible analysis in Python
GitHub is where people build software. More than 28 million people use GitHub to discover, fork, and contribute to over 85 million projects.
reproducible-research  python 
12 days ago
Supercomputing how Fish Save Energy Swimming in Schools - insideHPC
Researchers also gained detailed knowledge about this process, which may have implications for energy-efficient swimming or flying swarms of drones.
reinforcement-learning  cfd 
12 days ago
academic_advisory/what_DS_do.md at master · brohrer/academic_advisory · GitHub
GitHub is where people build software. More than 28 million people use GitHub to discover, fork, and contribute to over 85 million projects.
data-science  careers 
14 days ago
Sunsetting Python 2 support
A pledge to drop Python 2 support by 2020.
python3  python 
16 days ago
Reproducibility in ML: Why It Matters and How to Achieve It
We make training and deploying deep models faster, cheaper, and better.
reproducible-research  machine-learning 
17 days ago
What interactives can do (that articles can’t)
It’s a tough time for interactives. Last year saw debates around whether the format is dead (or not) and it’s difficult not to notice an industry-wide trend ...
interactive  data-visualization 
18 days ago
cuttlefishh/python-for-data-analysis: An introduction to data science using Python and Pandas with Jupyter notebooks.
GitHub is where people build software. More than 27 million people use GitHub to discover, fork, and contribute to over 80 million projects.
python  data-science  jupyter-notebook  online  training 
19 days ago
snipsco/snips-nlu: Snips Python library to extract meaning from text
GitHub is where people build software. More than 27 million people use GitHub to discover, fork, and contribute to over 80 million projects.
python  natural-language-processing  library 
19 days ago
Reeborg's World
Free Interactive Programming Tutorials
python  learning  online  interactive 
19 days ago
Saving Half-Done Work With Git Stash - DZone DevOps
This article can teach you to use the git stash command to store unwritten work without committing it, as well as other commands to edit, delete, and recall.
git 
19 days ago
The Elements of AI - a free online course
Learn more about the University of Helsinki and Reaktor's upcoming AI course for students and business professionals - no programming or math skills required.
online  course  machine-learning  artificial-intelligence  training 
22 days ago
Why you need to improve your training data, and how to do it « Pete Warden's blog
There are lots of good reasons why researchers are so fixated on model architectures, but it does mean that there are very few resources available to guide people who are focused on deploying machine learning in production. To address that, my talk at the conference was on “the unreasonable effectiveness of training data”, and I want to expand on that a bit in this blog post, explaining why data is so important along with some practical tips on improving it.

machine-learning  training  data-acquistion 
23 days ago
Free E-books | Syncfusion | Succinctly Series | HoloLens Succinctly
Microsoft’s HoloLens applications exist in the ever-expanding realm of mixed reality. In HoloLens Succinctly, author Lars Klint guides readers into the various segments of this augmented world, outlining the architecture of HoloLens apps, exploring code and design issues, and offering step-by-step instruction on inputting data so that users can collaborate and share their own hologram projects.

hololens  book  online 
23 days ago
Learning Machine Learning — Way of the Geophysicist
Machine Learning for Non-Coders can seem daunting. This is a collection of resources to pick up anyone at any level and get them into deep learning. Most resources are free or budget friendly. Every category has alternatives to chose from.
machine-learning  resources  learning 
23 days ago
Why Blockchain Poses an Unusual Challenge for GDPR Compliance | Legaltech News
Many of GDPR’s biggest mandates are fundamentally incompatible with blockchain technology. How can blockchain operators find common ground with the new regulation?
blockchain  privacy 
23 days ago
Feature Engineering and Selection: A Practical Approach for Predictive Models
The goals of Feature Engineering and Selection are to provide tools for re-representing predictors, to place these tools in the context of a good predictive modeling framework, and to convey our experience of utilizing these tools in practice. In the end, we hope that these tools and our experience will help you generate better models. When we started writing this book, we could not find any comprehensive references that described and illustrated the types of tactics and strategies t...
online  book  feature-learning  machine-learning 
25 days ago
Feature Engineering and Selection: A Practical Approach for Predictive Models
Feature Engineering and Selection: A Practical Approach for Predictive Models
predictive-modeling  online  books 
25 days ago
Hyperparameter Optimization with Keras – Towards Data Science
GitHub is where people build software. More than 27 million people use GitHub to discover, fork, and contribute to over 80 million projects.
machine-learning  keras  hyper-parameters  deep-learning 
25 days ago
« earlier      
3d 3d-printing 3d-scanning accessibility afrl ajax algorithms analytics android api application architecture arduino aria artificial-intelligence augmented-reality awesome benchmark big-data biomimicry biomimicry_petal biomimicry_petal_angeera biomimicry_petal_calvin biomimicry_petal_colleen biomimicry_petal_herb biomimicry_petal_nick biomimicry_petal_victoria biomimicry_petal_vik blog book books browser camera career cave cfd cheatsheet cloud cloudcomputing code collaboration color comparison computational computer computing course css d3 data data-cleanup data-management data-science data-visualization debugging deep-learning design development docker editor education example examples filetype:pdf flash forms fortran framework free gallery git google government gpu graphics grcsmac grcsocnet gui guide guidelines haptics hdf5 head-mounted-displays health high high-performance-computing history hololens html html5 image image-processing images immersive infographic infographics interactive interfaces ipython javascript jquery jupyter jupyter-notebook kinect leap leap-motion learning libraries library linux mac machine-learning management media:document medical medicine memory microsoft mixed-reality mobile modeling motion mpi nasa nasagrcsocnet natural natural-user-interfaces neural-network notebook oculus oculus-rift online open-source opensource optimization overview pandas parallel pdf performance ping.fm plotting policy presentations processing profiling programming project provenance pycon python r raspberry-pi reality reference reproducible reproducible-research research resources responsive rift robotics science scientific scientific-computing scientific-data-management scratch scripting search secondlife security selenium seo socialmedia socialnetworking software standards statistics telepresence tensorflow testing tips tool tools toread towatch tracking training tutorial tutorials twitter unity usability user validation video videos virtual virtual-reality virtualworlds visualization vive watched watson web web2.0 webdesign webdev webgl webvr workflow

Copy this bookmark:



description:


tags: